opensage-agent
Official@opensage-agent
Orchestrates multi-agent sessions using Neo4j graph databases, Joern static analysis, and AFL++ fuzzing for deep codebase architectural evaluation and security testing.
Agent Skills by opensage-agent
Showing 32 vetted skills indexed across 1 GitHub repositories.
opensage-adk
Orchestrate multi-agent sessions with sandboxed tools and Neo4j memory.
neo4j-query
Execute arbitrary Cypher queries against Neo4j graph databases to retrieve structured JSON records.
mmp
Multiplexes multiple MCP server connections via CLI across http, sse, stdio transports with persistent sessions.
create-new-tool
Scaffold bash tool directories with SKILL.md templates and executable scripts.
setup-matt-pocock-skills
Standardizes repository-level agent configs for GitHub, GitLab, and local markdown environments.
joern-query
Execute custom Joern queries against a code property graph for static analysis.
improve-codebase-architecture
Analyzes module structure and proposes deep redesigns for fragmented codebases.
triage
Manage GitHub issue lifecycle through state machine and role-based classification.
prototype
Build throwaway terminal applications to test state machines and UI variations.
diagnose
Diagnose software defects and performance regressions through structured hypothesis testing.
to-issues
Decompose project plans into granular vertical slice issues with dependencies and acceptance criteria.
zoom-out
Map modules and callers to provide architectural context for large codebases.
retrieval
Search code symbols with ctags and analyze functions via Neo4j.
workflow
Orchestrate multi-agent systems with ensemble, pool, and retry patterns.
grill-with-docs
Validate design plans against domain models and architectural decision records.
fuzz
Automate AFL++ fuzzing campaigns with custom mutators and crash extraction.
tdd
Plan and execute vertical slices with tracer bullets for test-driven development.
to-prd
Synthesize conversation context and codebase knowledge into structured Product Requirements Documents.
get-caller
Identify direct and indirect callers of functions using Neo4j callgraph data.
search-function
Locate function definitions by querying a Neo4j static analysis database.
get-call-paths
Query a Neo4j graph database to identify call paths between source and destination functions.
joern-slice
Extract program slices for specific functions using Joern static analysis.
get-callee
Queries a Neo4j database to analyze direct and indirect function call graphs.
list-functions
List function definitions and line ranges in source files via Neo4j queries.
Frequently Asked Questions About opensage-agent
FAQPage SchemaWhat specific tasks can I perform with these capabilities?▼
You can execute complex static analysis via Joern, map function call graphs using Neo4j, perform directed binary fuzzing with AFL++, and decompose project requirements into structured vertical slices. These capabilities enable deep architectural introspection and rigorous security testing within your existing development environment.
Which personas benefit most from these technical capabilities?▼
Security researchers, software architects, and senior backend engineers benefit most. These capabilities are designed for professionals managing large, fragmented codebases who require deep visibility into function call hierarchies, static analysis of code property graphs, and systematic fuzzing for vulnerability discovery.
What are the primary prerequisites for running these functions?▼
You require a configured Neo4j instance for graph data storage, a Joern installation for static analysis, and an environment capable of running AFL++ for fuzzing campaigns. Additionally, your repository must support standard markdown-based configuration files to integrate with the provided multi-agent orchestration patterns.